Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Ashirth Barthur, Security Scientist, H2O, at MLconf Seattle 2017

535 views

Published on

Ashrith Barthur is a Security Scientist at H2O currently working on algorithms that detect anomalous behaviour in user activities, network traffic, attacks, financial fraud and global money movement. He has a PhD from Purdue University in the field of information security, specialized in Anomalous behaviour in DNS protocol.

Abstract summary

ML(Machine Learning) in AML (Anti Money Laundering):
AML or anti money laundering has been a consistent bane of multiple governments and banks. A strong influences by countries to curb illegal money movement has resulted in a significant yet extremely small aspect of money laundering being identified – a success rate of about 2% average. A more global foot print the bank has the lesser is the accuracy of money laundering investigations. In its current mechanism, investigators analyse each money laundering alert and provide their subjective opinion towards a case. Unfortunately this takes time, and still has a return rate of about 2% at average and 10% at the highest. What we design are AI algorithms that work upon features that track monetary behaviour of every account. These features are essentially time-bound making them a fundamental aspect of algorithm design. The algorithms have a capability to improve the identification close to 70%, and we a certain exclusive features that are a function of time and improve much further.

Published in: Technology
  • Be the first to comment

  • Be the first to like this

Ashirth Barthur, Security Scientist, H2O, at MLconf Seattle 2017

  1. 1. H2 O.ai Machine Intelligence Anti-Money Laundering Solution
  2. 2. H2 O.ai Machine Intelligence What is Money Laundering? 1. “Washing” ill-gotten money with legitimate money to hide the source 2. Illegal drug sales, human trafficking, online gambling, insider trading, etc.
  3. 3. H2 O.ai Machine Intelligence What is the problem with Money Laundering? 1. Illegal trade and markets grow 2. Negatively impacts the society 3. Governments lose out on taxes 4. In some countries, alternative centers of power come into existence.
  4. 4. H2 O.ai Machine Intelligence Solutions do exist. Right? 1. Yes. 2. But are limited 3. Limited due to current rule-based, stateless approach
  5. 5. H2 O.ai Machine Intelligence So what do we do? 1. Up the game 2. Make the detecting systems smarter
  6. 6. H2 O.ai Machine Intelligence One Solution is to use Machine Learning - Artificial Intelligence
  7. 7. H2 O.ai Machine Intelligence AML Solution Evolution Rule-based Model Feature-based Model Pure Data Driven Model
  8. 8. H2 O.ai Machine Intelligence Rule-based Model Alerts from rule-based system Analytical Inputs: 1. LexisNexis 2. Accounts Database 3. Transaction Database 4. Card Database Alert Decision: Suspicious Alert Decision: Not Suspicious
  9. 9. H2 O.ai Machine Intelligence Rule-based Model: Limitations 1. Manual analysis by an investigator 2. Dispersed datasets 3. Subjective and inconsistent 4. Time consuming 5. High false positive rate
  10. 10. H2 O.ai Machine Intelligence AML Solution Evolution Rule-based Model Feature-based Model Pure Data Driven Model
  11. 11. H2 O.ai Machine Intelligence Features - (Used in Feature-based Model) 1. Features are meta data (Extracted from the data) 2. They help algorithms capture information from the data. 3. Feature engineering is a form of language translation: Between raw data and the algorithm.
  12. 12. H2 O.ai Machine Intelligence Source of Features 1. Transactions - or payments databases 2. Account Information - customer focused database 3. Alerts - AML alerts database.
  13. 13. H2 O.ai Machine Intelligence Features - Example average balance of last 7 days 7 Days
  14. 14. H2 O.ai Machine Intelligence Features: Advantages 1. Designed Features Highlight Transactional Behaviour 2. Features Continuously Track Transactional Behaviour of an account 3. Rules Variables can only Identify Threshold Changes
  15. 15. H2 O.ai Machine Intelligence Feature-based Model Alerts from rule-based system Alert Decision: Not Suspicious H2O Machine Learning Algorithm Alert Decision: Suspicious Analytical Inputs: 1. Transaction Data 2. Account Data 3. Card Data etc.
  16. 16. H2 O.ai Machine Intelligence Feature-based Model: Advantages 1. Uses AI - artificial intelligence 2. AI with features uses a consistent and objective approach 3. Quick classification 4. Low false positive rate - tweaked based on risk appetite.
  17. 17. H2 O.ai Machine Intelligence Feature-based Model Workflow Alerts from rule-based system Alert Decision: Not Suspicious H2O Machine Learning Algorithm Alert Decision: Suspicious Analytical Inputs: 1. Transaction Data 2. Account Data 3. Card Data etc. AML Analyst Alert decision sampling by the analyst Algorithm tuning by analyst after alert decision sampling
  18. 18. H2 O.ai Machine Intelligence AML Solution Evolution Rule-based Model Feature-based Model Pure Data Driven Model
  19. 19. H2 O.ai Machine Intelligence Pure Data-driven Model Not a suspicious transaction H2O Machine Learning - Deep Learning Algorithm Suspicious Transaction Transaction Data Alert Data Card Data Account Data
  20. 20. H2 O.ai Machine Intelligence Pure Data-driven Model: Advantages 1. The algorithm understands malicious behaviour through data 2. Algorithm is smart to work without features - metadata 3. Does not need alerts for training 4. Helps in identifying any kind of anomalous behaviour 5. Deeper insights about customer
  21. 21. H2 O.ai Machine Intelligence Thank You Questions?

×